Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add chocomyong/harness-kit --skill canon-upkeepgit clone --depth 1 https://github.com/chocomyong/harness-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chocomyong/harness-kit/canon-upkeep)<a href="https://agentmods.dev/skills/chocomyong/harness-kit/canon-upkeep"><img src="https://agentmods.dev/badge/skills/chocomyong/harness-kit/canon-upkeep/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chocomyong/harness-kit/canon-upkeep"><img src="https://agentmods.dev/badge/skills/chocomyong/harness-kit/canon-upkeep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00316 |
| Opus 5.5 | $0.00021 | $0.00126 |
| Sonnet 5.5 | $0.00010 | $0.00063 |
| Haiku 4.5 | $0.00005 | $0.00032 |
Grade A, and why
canon-upkeep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Keep the canon current
A rules file that drifts from the repo becomes noise, and a stale fact gets quoted as true.
Steps
- Find when the canon last changed:
git log -1 --format=%ad -- AGENTS.md docs/REPO_MAP.md. - Survey what changed since then:
git log --since=<that date> --stat, new or moved modules, retired code. - Propose updates from measured facts only:
docs/REPO_MAP.mdrows, names, and runtime values, each re-measured with its command;- rules that no longer match how the repo works;
- counts or versions that crept into docs - replace with the command that produces them.
- Check the size budget: the always-loaded rules file stays under ~150 lines. Move facts to the repo map, area knowledge to on-demand files, and enforceable rules to hooks.
- Grep for each changed rule's key phrase across the repo. A rule stated in two files is edited in both or replaced by a link.
- Show the diff. Never weaken the top invariant, and never delete a rule only because you do not understand it - ask.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 25 lines · 52 tokens per session scan A eb33d0d2230e
canon-upkeep is a skill published in the GitHub repository chocomyong/harness-kit (2 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 316 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other skills, from other repositories
openrig-user
Use when a specific rig command, subcommand, or flag is already known and you need its exact syntax, JSON shape, defaults, or error meaning. NOT for natural capability discovery, open-ended how-do-I questions, or choosing which OpenRig move applies.
applying-a-permission-policy
Use before launching a team during agent-guided setup, or when a user asks to configure OpenRig command permissions, reduce repeated native approval prompts, or apply a selected rig/seat permission policy.
forming-an-openrig-mental-model
Use when the system around you does not make sense yet: you just booted into a seat and do not know how the pieces fit; someone said rig, pod, seat, fleet, topology, or slice and you are not certain what they mean here; you are unsure what kind of rig you are in or what it is for; you do not know how skills reach you…
openrig-software-factory
Use when a user wants a continuing software team for a real repository, or has a first OpenRig team and needs a repeatable path for reviewed work and later tasks.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
agent-starters
Use when creating, refreshing, packaging, inspecting, promoting, or deprecating a named per-seat starting point — Agent Starter manifest authoring, the 6-state lifecycle (captured → named → inspectable → used → promoted → deprecated), provenance honesty, and refusal rules. NOT a VM image; a managed starting point…